How to Use the EOD Historical Data MCP in CrewAI

Q: How do I assign specific EOD Historical Data tools to different agents in CrewAI?

You use the MCPServerHTTP class with a toolfilter to expose only specific tools, like geteodhistorical to your charting agent and getfundamentals to your valuation agent. This prevents your agents from getting confused by too many available tools.

Q: Can CrewAI agents share data retrieved from EOD Historical Data?

Yes, CrewAI's shared memory allows an agent using getinsidertransactions to pass its findings directly to another agent running technical analysis. The receiving agent uses this context to refine its market predictions without re-querying the API.

Q: How do I connect the EOD Historical Data MCP Server to a CrewAI python script?

You pass your Vinkius HTTP endpoint URL directly into the mcps parameter of your CrewAI Agent definition. The framework automatically registers the 26 financial tools and makes them available for your agents to invoke during their tasks.

Deploy a collaborative crew of financial agents to analyze EOD Historical Data autonomously.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect EOD Historical Data MCP to CrewAI

Create your Vinkius account to connect EOD Historical Data to CrewAI and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup EOD Historical Data with CrewAI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Coordinate specialized investment crews using CrewAI

The `get_fundamentals` tool supplies deep corporate financial statements to your research crew. In a CrewAI setup, an Analyst Agent pulls this raw fundamental data, while a separate Writer Agent compiles it into a structured investment memo. These agents share memory, meaning the Writer Agent knows exactly what the Analyst Agent discovered via `get_dividends` or `get_splits`. This collaborative approach replaces single-prompt models with a structured, multi-perspective analysis pipeline.

Track market narratives with an autonomous MCP Server crew

The `get_news` tool feeds real-time financial news articles directly into your CrewAI monitoring loop using this MCP server. A dedicated News Agent filters these articles using `get_news_word_weights` to identify trending topics and critical market events. The News Agent then passes its findings to a Risk Agent, which queries `get_technical_indicators` to assess if the news warrants a portfolio rebalance. The entire process runs autonomously, using CrewAI's hierarchical execution to escalate critical alerts.

Analyze sovereign debt trends with multi-agent workflows

The `get_ust_yield_rates` tool provides the raw yield data needed to evaluate sovereign debt markets. Your macroeconomic crew assigns a Debt Specialist Agent to monitor these yields alongside `get_ust_real_yield_rates` to calculate real returns. A second Portfolio Agent ingests these real yields to adjust asset allocation recommendations. CrewAI manages the secure handoffs between these specialized agents, ensuring your macro strategy stays updated without human intervention.

Setup guide

Set up EOD Historical Data MCP in CrewAI

Prerequisites

Python 3.10+ installed
crewai package (pip install crewai)
Active Vinkius subscription with a valid endpoint token

1

Install CrewAI
Run pip install crewai to install the framework. MCP support is built-in via the mcps parameter.
2

Add the MCP URL to your agent
Pass your Vinkius endpoint directly to the mcps list. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. CrewAI handles tool discovery and caching automatically.
3

Kick off your crew
Create a Crew with your agent and tasks. Call crew.kickoff() — the agent will automatically invoke EOD Historical Data tools as needed.

crew.py

from crewai import Agent, Task, Crew

agent = Agent(
    role="EOD Historical Data Analyst",
    goal="Access and analyze EOD Historical Data data via MCP.",
    backstory="Expert analyst with direct EOD Historical Data access.",
    mcps=[
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ],
)

task = Task(
    description="List recent EOD Historical Data transactions",
    agent=agent,
    expected_output="A summary of recent activity",
)

crew = Crew(agents=[agent], tasks=[task])
result = crew.kickoff()
print(result)

Get your connection token →

Prerequisites

Python 3.10+ installed
crewai + crewai-tools packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install crewai crewai-tools. The MCPServerAdapter handles lifecycle management and tool conversion.
2

Connect with MCPServerAdapter
Use MCPServerAdapter as a context manager with SseServerParameters pointing to your Vinkius endpoint. The adapter automatically manages connection lifecycle.
3

Assign tools and run
Pass the returned mcp_tools to your agent's tools parameter. The adapter converts MCP tools to native BaseTool objects compatible with all CrewAI agents.

crew.py

from crewai import Agent, Task, Crew
from crewai_tools import MCPServerAdapter
from mcp import SseServerParameters

server_params = SseServerParameters(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

with MCPServerAdapter(server_params) as mcp_tools:
    agent = Agent(
        role="EOD Historical Data Analyst",
        goal="Access and analyze EOD Historical Data data via MCP.",
        backstory="Expert analyst with direct EOD Historical Data access.",
        tools=mcp_tools,
    )

    task = Task(
        description="List recent EOD Historical Data transactions",
        agent=agent,
        expected_output="A summary of recent activity",
    )

    crew = Crew(agents=[agent], tasks=[task])
    result = crew.kickoff()
    print(result)

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by EOD Historical Data. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect EOD Historical Data now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about EOD Historical Data MCP in CrewAI

You use the `MCPServerHTTP` class with a `tool_filter` to expose only specific tools, like `get_eod_historical` to your charting agent and `get_fundamentals` to your valuation agent. This prevents your agents from getting confused by too many available tools.

Yes, CrewAI's shared memory allows an agent using `get_insider_transactions` to pass its findings directly to another agent running technical analysis. The receiving agent uses this context to refine its market predictions without re-querying the API.

You pass your Vinkius HTTP endpoint URL directly into the `mcps` parameter of your CrewAI Agent definition. The framework automatically registers the 26 financial tools and makes them available for your agents to invoke during their tasks.

CrewAI executes tasks sequentially or hierarchically, meaning one agent can find tickers using `search_assets` and hand them to a second agent that fetches historical pricing using `get_eod_historical`.

No, all queries sent to this MCP server are routed directly to the EOD Historical Data API through an encrypted, ephemeral V8 isolate. Your portfolio tickers, dividend queries, and search queries are never stored or used to train models.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript